bioc-pmc-api

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to fetch and parse full-text articles from the public NCBI BioC-PMC API (https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/...), meaning it ingests untrusted third-party PMC content as part of its workflow which could materially influence decisions or actions.